ai-evals

Community

Design AI evals for confident shipping.

Authoroldwinter
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a structured framework for designing and executing evaluations of AI/LLM features, ensuring quality, safety, and performance before deployment.

Core Features & Use Cases

  • Eval PRD Creation: Define clear evaluation requirements, scope, and acceptance thresholds.
  • Test Set & Taxonomy Development: Build golden test sets and error taxonomies from failure analysis.
  • Rubric & Judge Planning: Design scoring rubrics and select appropriate judging approaches (human, LLM-as-judge).
  • Use Case: You've developed a new AI assistant for customer support. Use this Skill to create a comprehensive evaluation plan, including test cases, a scoring rubric, and a process for analyzing results to ensure it meets quality and safety standards before launch.

Quick Start

Use the ai-evals skill to design an evaluation plan for a new AI feature.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ai-evals
Download link: https://github.com/oldwinter/skills/archive/main.zip#ai-evals

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.